Deep learning-based canopy gap detection using a cross-technological approach with airborne laser scanning and aerial imagery data

Canopy gap detection in three enlarged subareas (white rectangles).

This repository contains code for forest canopy gap detection using a deep learning model trained on gaps automatically generated from airborne laser scanning (ALS)-derived canopy height models (CHMs), combined with spectral (true digital orthophotos) and height information from digital aerial photogrammetry (DAP)-based CHMs. For further details, see the following paper:

Franz, F., Seidel, D., Beckschäfer, P., 2025. Deep learning-based canopy gap detection using a cross-technological approach with airborne laser scanning and aerial imagery data. Ecol. Informatics.

Folder structure

Requirements

  • R 4.4.0
  • Python 3.10.12

Citation

@article{franz2025deep,
  title={Deep learning-based canopy gap detection using a cross-technological approach with airborne laser scanning and aerial imagery data},
  author={Franz, Florian and Seidel, Dominik and Becksch{\"a}fer, Philip},
  journal={Ecological Informatics},
  pages={},
  year={2025},
  publisher={Elsevier}
}